© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 14462
    Prev
    Next
    INDEX
    Explanations

    pronouns and references to characters' actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    дап
    -0.08
    ÑĸннÑı
    -0.07
     FUNC
    -0.07
    .cf
    -0.07
    оген
    -0.07
    905
    -0.07
    ruba
    -0.07
    CTR
    -0.06
    CTS
    -0.06
    ripp
    -0.06
    POSITIVE LOGITS
     suddenly
    0.11
     again
    0.08
     sudden
    0.07
     notice
    0.07
    zb
    0.07
     became
    0.07
     Suddenly
    0.06
    çªģçĦ¶
    0.06
    ki
    0.06
     began
    0.06
    Activations Density 0.047%

    No Known Activations